Full infrastructure intelligence in 48 hours. Book the assessment →
Client login Talk to sales Book the assessment

IDE · WORKBENCH

One workbench, from the hotspot to the rollout.

The workbench is where the assessment turns into engineering. A native, GPU-rendered editor on a Rust foundation, with the hotspot list, the agent panel, the benchmark receipts and the deploy panel in the same window.

Book the 48-hour assessmentTalk to sales
Workbench: the costliest function in production open at its definition, the Loop's review packet beside it

Overview

FlexLab is a unified workbench: Code, Build, Browse, Board, Connect, Benchmark and more under one mode switcher, native on desktop, in the browser, on iOS and Android. It hosts the loop end to end: the telemetry feed from Assess, the translation engine, the benchmark receipts and the compute grid's pins.

HOTSPOTS PANEL

Production's most expensive functions, in your editor.

  • Task efficiency and task demand joined per function: failure rate, latency percentiles, peak CPU, calls per day, cadence
  • Ranked by what it costs, with confidence attached
  • One click hands the unit to an agent together with its golden cases
Tasks: every background job's events, success rate and tail latency, flagged when slow
AGENT PANEL

Any agent. One permission boundary.

  • Claude, Codex, Copilot, Grok or any Agent Client Protocol agent, in the same panel
  • Typed tools behind a permission boundary: list_hotspots, first_golden_case, placement_quote, report_kernel_candidate, rebuild_grain, deploy_grain
  • Plan, act, observe with checkpoints and undo; termination ceilings, no runaway loops
Workbench: the kernels the agent identified in production, each with its first golden case and a Translate action
THE EDITOR

A native editor, not a web view.

  • Rust and GPUI, GPU-rendered, local-first: opens in milliseconds and stays fast on large trees
  • Multi-mode editor: code, grid, rich text, VIM
  • Edit prediction from Copilot, Codestral or a local Ollama
Workbench: the native editor at the costliest function's definition
COLLABORATION

Shared sessions with signed provenance.

  • CRDT documents that converge, over WebTransport
  • Every edit carries an ed25519 signature: who changed what, provably
  • Voice inside the session, no third-party call
Workbench: the team's floor, who is on it and the day's calendar
BENCHMARK & DEPLOY PANELS

Approve a receipt. Deploy to shadow. Roll back.

  • Nothing deploys without an approved receipt
  • A deploy lands as a shadow pin; promotion is a separate, guarded step
  • A rebuilt grain must earn its receipt again
Workbench: a translated kernel on canary, its promotion console with promote and roll back
SHEET, DRAW, NEWS, EXTENSIONS

The rest of the workbench.

  • Sheet, diagrams and news live beside the code, not in another tab
  • Extensions run as WASM in a jail
  • Signed self-update; entitlement leases verifiable offline
Workbench: a Pareto board, gross margin by product
Tasks: every background job's events, success rate and tail latency, flagged when slow
Workbench: the kernels the agent identified in production, each with its first golden case and a Translate action
Workbench: the native editor at the costliest function's definition
Workbench: the team's floor, who is on it and the day's calendar
Workbench: a translated kernel on canary, its promotion console with promote and roll back
Workbench: a Pareto board, gross margin by product

BEFORE YOU START

Before you start

Do we have to switch editors?

No. The loop is also exposed as MCP tools and a VS Code extension. The workbench is where it is fastest, not the only place it runs.

Which agents?

Claude, Codex, Copilot and Grok today, plus any agent speaking the Agent Client Protocol. All behind the same typed tools and permission boundary.

Where does it run?

Native on macOS, Windows and Linux, in the browser, and on iOS and Android.

FLEX AXION

Five stages. One signal.

Compute Intelligence. Accelerated.